Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=true, and the description usefully adds that matching is deterministic (no LLM) with stated criteria (same category, shared tag, compatible network) and ranking (freshness then ID). However, it says nothing about how many results come back, how pagination behaves, or any auth/visibility constraints, which are the remaining behavioral gaps for a read tool with a cursor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence that front-loads the core behavior and packs in criteria, ranking, and the output key format with no filler. It is terse to the point of being telegraphic, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description helpfully specifies the returned identifier format and ordering, which is exactly what an agent needs to interpret results. It falls short on the input side, leaving limit/cursor behavior unexplained for a paginated, zero-required-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% — only resource_id carries a description ('Optional want ID'), while limit and cursor are undocumented. The description does not compensate: the 'want_id:offer_id' output format hints at resource_id's role but adds no detail on limit bounds or cursor semantics, so an agent must guess at pagination behavior.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific operation (deterministic want→offer matching) and even gives the output key format ('want_id:offer_id'), so the agent knows exactly what this produces. It implies differentiation from the list_* siblings via 'matches' rather than plain listing, but never names an alternative tool explicitly, which keeps it short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit statement of when to call this versus list_wants/list_offers or how it relates to them. Usage is only inferable from the verb 'suggest_matches'; no exclusions, prerequisites, or alternative-routing guidance are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.